[PATCH net-next 0/4][pull request] Intel Wired LAN Driver Updates 2026-09-01 (i40e)

[PATCH net-next 0/4][pull request] Intel Wired LAN Driver Updates 2026-09-01 (i40e)

[Tony Nguyen]

Kohei Enju adds support for XDP metadata of Rx hash and VLAN tag.

Chris Packham reduces messaging when Rx filters are exhausted, and
promiscuous mode is enabled, to occur once when the mode is enabled
rather than repeated messaging for each filter.
---
These are the i40e patches split off from this PR:
https://lore.kernel.org/netdev/20260805213541.2281287-1-anthony.l.nguyen@intel.com/

The following are changes since commit c8ea08ba34f2a2e9bfb18ff3d69eb2d69b324f49:
  Merge branch 'netlink-specs-rt-link-ipv6-devconf-updates'
and are available in the git repository at:
  git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/next-queue 40GbE

Chris Packham (1):
  i40e: Avoid repeating RX filter warning

Kohei Enju (3):
  i40e: prepare for XDP metadata ops support
  i40e: add support for bpf_xdp_metadata_rx_hash()
  i40e: add support for bpf_xdp_metadata_rx_vlan_tag()

 drivers/net/ethernet/intel/i40e/i40e_main.c | 70 ++++++++++++++++++---
 drivers/net/ethernet/intel/i40e/i40e_txrx.c |  5 +-
 drivers/net/ethernet/intel/i40e/i40e_txrx.h |  7 ++-
 drivers/net/ethernet/intel/i40e/i40e_type.h |  5 ++
 drivers/net/ethernet/intel/i40e/i40e_xsk.c  | 12 ++++
 5 files changed, 88 insertions(+), 11 deletions(-)

-- 
2.47.1

[PATCH net-next 1/4] i40e: prepare for XDP metadata ops support

[Tony Nguyen]

From: Kohei Enju <kohei@enjuk.jp>

Prepare 'struct i40e_xdp_buff' that contains an xdp_buff and a pointer
to i40e_rx_desc in order to pass the RX descriptor to the XDP kfuncs.
Also in ZC path, use XSK_CHECK_PRIV_TYPE() to ensure i40e_xdp_buff
doesn't exceed the offset of cb in xdp_buff_xsk.

No functional changes.

Signed-off-by: Kohei Enju <kohei@enjuk.jp>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Tested-by: Patryk Holda <patryk.holda@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c |  2 +-
 drivers/net/ethernet/intel/i40e/i40e_txrx.c |  5 ++++-
 drivers/net/ethernet/intel/i40e/i40e_txrx.h |  7 ++++++-
 drivers/net/ethernet/intel/i40e/i40e_xsk.c  | 12 ++++++++++++
 4 files changed, 23 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 0cd0e5597c90..4b11ae9ed8d5 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -3622,7 +3622,7 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 	}
 
 skip:
-	xdp_init_buff(&ring->xdp, xdp_frame_sz, &ring->xdp_rxq);
+	xdp_init_buff(&ring->xdp_ctx.xdp, xdp_frame_sz, &ring->xdp_rxq);
 
 	rx_ctx.dbuff = DIV_ROUND_UP(ring->rx_buf_len,
 				    BIT_ULL(I40E_RXQ_CTX_DBUFF_SHIFT));
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index ef5e657816f0..7f68adb5109b 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -2438,10 +2438,11 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget,
 			     unsigned int *rx_cleaned)
 {
 	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
+	struct i40e_xdp_buff *xdp_ctx = &rx_ring->xdp_ctx;
 	u16 cleaned_count = I40E_DESC_UNUSED(rx_ring);
 	u16 clean_threshold = rx_ring->count / 2;
 	unsigned int offset = rx_ring->rx_offset;
-	struct xdp_buff *xdp = &rx_ring->xdp;
+	struct xdp_buff *xdp = &xdp_ctx->xdp;
 	unsigned int xdp_xmit = 0;
 	struct bpf_prog *xdp_prog;
 	bool failure = false;
@@ -2530,6 +2531,8 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget,
 		if (neop)
 			continue;
 
+		xdp_ctx->desc = rx_desc;
+
 		xdp_res = i40e_run_xdp(rx_ring, xdp, xdp_prog);
 
 		if (xdp_res) {
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index 1e5fd63d47f4..bb741ff3e5f2 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -283,6 +283,11 @@ struct i40e_rx_buffer {
 	__u32 page_count;
 };
 
+struct i40e_xdp_buff {
+	struct xdp_buff xdp;
+	const union i40e_rx_desc *desc;
+};
+
 struct i40e_queue_stats {
 	u64 packets;
 	u64 bytes;
@@ -345,7 +350,7 @@ struct i40e_ring {
 	 * and to resume packet building for this ring in the next call to
 	 * i40e_clean_rx_ring_irq().
 	 */
-	struct xdp_buff xdp;
+	struct i40e_xdp_buff xdp_ctx;
 
 	/* Next descriptor to be processed; next_to_clean is updated only on
 	 * processing EOP descriptor
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index 9f47388eaba5..51a05ce4c7ce 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -246,6 +246,8 @@ bool i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 count)
 	u32 nb_buffs, i;
 	dma_addr_t dma;
 
+	XSK_CHECK_PRIV_TYPE(struct i40e_xdp_buff);
+
 	rx_desc = I40E_RX_DESC(rx_ring, ntu);
 	xdp = i40e_rx_bi(rx_ring, ntu);
 
@@ -396,6 +398,14 @@ static void i40e_handle_xdp_result_zc(struct i40e_ring *rx_ring,
 	WARN_ON_ONCE(1);
 }
 
+static struct i40e_xdp_buff *xsk_buff_to_i40e_ctx(struct xdp_buff *xdp)
+{
+	/* xdp_buff pointer used by ZC code path is allocated as xdp_buff_xsk.
+	 * i40e_xdp_buff private fields overlap with xdp_buff_xsk->cb.
+	 */
+	return (struct i40e_xdp_buff *)xdp;
+}
+
 /**
  * i40e_clean_rx_irq_zc - Consumes Rx packets from the hardware ring
  * @rx_ring: Rx ring
@@ -472,6 +482,8 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
 		if (i40e_is_non_eop(rx_ring, rx_desc))
 			continue;
 
+		xsk_buff_to_i40e_ctx(first)->desc = rx_desc;
+
 		xdp_res = i40e_run_xdp_zc(rx_ring, first, xdp_prog);
 		i40e_handle_xdp_result_zc(rx_ring, first, rx_desc, &rx_packets,
 					  &rx_bytes, xdp_res, &failure);
-- 
2.47.1

[PATCH net-next 2/4] i40e: add support for bpf_xdp_metadata_rx_hash()

[Tony Nguyen]

From: Kohei Enju <kohei@enjuk.jp>

Introduce i40e_xdp_rx_hash() which takes the same approach as
i40e_rx_hash() to extract the hash from RX descriptors.

Tested with X710 adapter using xdp_hw_metadata, and verified hash
consistency between bpf_xdp_metadata_rx_hash() and skb->hash.

Signed-off-by: Kohei Enju <kohei@enjuk.jp>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Tested-by: Patryk Holda <patryk.holda@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c | 30 +++++++++++++++++++++
 drivers/net/ethernet/intel/i40e/i40e_type.h |  5 ++++
 2 files changed, 35 insertions(+)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 4b11ae9ed8d5..e487d697a634 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -4,6 +4,7 @@
 #include <generated/utsrelease.h>
 #include <linux/crash_dump.h>
 #include <linux/net/intel/libie/pctype.h>
+#include <linux/net/intel/libie/rx.h>
 #include <linux/if_bridge.h>
 #include <linux/if_macvlan.h>
 #include <linux/module.h>
@@ -13582,6 +13583,34 @@ static int i40e_xdp(struct net_device *dev,
 	}
 }
 
+static int i40e_xdp_rx_hash(const struct xdp_md *_ctx, u32 *hash,
+			    enum xdp_rss_hash_type *rss_type)
+{
+	const struct i40e_xdp_buff *ctx = (const void *)_ctx;
+	const union i40e_rx_desc *desc = ctx->desc;
+	struct libeth_rx_pt rx_ptype;
+	u8 raw_rx_ptype;
+	u64 status;
+
+	status = le64_to_cpu(desc->wb.qword1.status_error_len);
+	raw_rx_ptype = FIELD_GET(I40E_RXD_QW1_PTYPE_MASK, status);
+	rx_ptype = libie_rx_pt_parse(raw_rx_ptype);
+
+	if (!libeth_rx_pt_has_hash(ctx->xdp.rxq->dev, rx_ptype) ||
+	    FIELD_GET(I40E_RX_DESC_STATUS_FLTSTAT_MASK, status) !=
+		    I40E_RX_DESC_FLTSTAT_RSS_HASH)
+		return -ENODATA;
+
+	*hash = le32_to_cpu(desc->wb.qword0.hi_dword.rss);
+	*rss_type = rx_ptype.hash_type;
+
+	return 0;
+}
+
+static const struct xdp_metadata_ops i40e_xdp_metadata_ops = {
+	.xmo_rx_hash		= i40e_xdp_rx_hash,
+};
+
 static const struct net_device_ops i40e_netdev_ops = {
 	.ndo_open		= i40e_open,
 	.ndo_stop		= i40e_close,
@@ -13784,6 +13813,7 @@ static int i40e_config_netdev(struct i40e_vsi *vsi)
 	i40e_vsi_config_netdev_tc(vsi, vsi->tc_config.enabled_tc);
 
 	netdev->netdev_ops = &i40e_netdev_ops;
+	netdev->xdp_metadata_ops = &i40e_xdp_metadata_ops;
 	netdev->watchdog_timeo = 5 * HZ;
 	i40e_set_ethtool_ops(netdev);
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h
index ed8bbdb586da..16a65c6e5153 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_type.h
@@ -4,6 +4,7 @@
 #ifndef _I40E_TYPE_H_
 #define _I40E_TYPE_H_
 
+#include <linux/bits.h>
 #include <uapi/linux/if_ether.h>
 #include "i40e_adminq.h"
 #include "i40e_hmc.h"
@@ -699,6 +700,10 @@ enum i40e_rx_desc_status_bits {
 	I40E_RX_DESC_STATUS_LAST /* this entry must be last!!! */
 };
 
+#define I40E_RX_DESC_STATUS_FLTSTAT_MASK                   \
+	GENMASK_ULL(I40E_RX_DESC_STATUS_FLTSTAT_SHIFT + 1, \
+		    I40E_RX_DESC_STATUS_FLTSTAT_SHIFT)
+
 #define I40E_RXD_QW1_STATUS_SHIFT	0
 #define I40E_RXD_QW1_STATUS_MASK	((BIT(I40E_RX_DESC_STATUS_LAST) - 1) \
 					 << I40E_RXD_QW1_STATUS_SHIFT)
-- 
2.47.1

Re: [PATCH net-next 2/4] i40e: add support for bpf_xdp_metadata_rx_hash()

[netdev-bot+sashiko]

Thank you for your contribution! Sashiko AI review found 1 potential
issue(s) to consider:

Critical: 0 · High: 0 · Medium: 1 · Low: 0

- [Medium] i40e_config_netdev() sets `netdev->xdp_metadata_ops =
  &i40e_xdp_metadata_ops;` unconditionally…

--

i40e: add support for bpf_xdp_metadata_rx_hash()

This adds i40e_xdp_rx_hash() as an xdp_metadata_ops callback, extracting
the RSS hash and hash type from the RX descriptor the same way
i40e_rx_hash() does. A new I40E_RX_DESC_STATUS_FLTSTAT_MASK helper is
added to i40e_type.h and the ops struct is installed on the netdev.

> diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
> index 4b11ae9ed8d53..e487d697a634f 100644
> --- a/drivers/net/ethernet/intel/i40e/i40e_main.c
> +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c

[ ... ]

> @@ -13582,6 +13583,34 @@ static int i40e_xdp(struct net_device *dev,
>  	}
>  }
>  
> +static int i40e_xdp_rx_hash(const struct xdp_md *_ctx, u32 *hash,
> +			    enum xdp_rss_hash_type *rss_type)
> +{
> +	const struct i40e_xdp_buff *ctx = (const void *)_ctx;
> +	const union i40e_rx_desc *desc = ctx->desc;
> +	struct libeth_rx_pt rx_ptype;
> +	u8 raw_rx_ptype;
> +	u64 status;
> +
> +	status = le64_to_cpu(desc->wb.qword1.status_error_len);
> +	raw_rx_ptype = FIELD_GET(I40E_RXD_QW1_PTYPE_MASK, status);
> +	rx_ptype = libie_rx_pt_parse(raw_rx_ptype);
> +
> +	if (!libeth_rx_pt_has_hash(ctx->xdp.rxq->dev, rx_ptype) ||
> +	    FIELD_GET(I40E_RX_DESC_STATUS_FLTSTAT_MASK, status) !=
> +		    I40E_RX_DESC_FLTSTAT_RSS_HASH)
> +		return -ENODATA;
> +
> +	*hash = le32_to_cpu(desc->wb.qword0.hi_dword.rss);
> +	*rss_type = rx_ptype.hash_type;
> +
> +	return 0;
> +}
> +
> +static const struct xdp_metadata_ops i40e_xdp_metadata_ops = {
> +	.xmo_rx_hash		= i40e_xdp_rx_hash,
> +};
> +
>  static const struct net_device_ops i40e_netdev_ops = {
>  	.ndo_open		= i40e_open,
>  	.ndo_stop		= i40e_close,

[ ... ]

> @@ -13784,6 +13813,7 @@ static int i40e_config_netdev(struct i40e_vsi *vsi)
>  	i40e_vsi_config_netdev_tc(vsi, vsi->tc_config.enabled_tc);
>  
>  	netdev->netdev_ops = &i40e_netdev_ops;
> +	netdev->xdp_metadata_ops = &i40e_xdp_metadata_ops;

[Severity: Medium]
Should this assignment live inside the I40E_VSI_MAIN branch, next to where
the rest of the XDP capability state is set?

Earlier in i40e_config_netdev() the XDP capabilities are set only for the
main VSI:

	if (vsi->type == I40E_VSI_MAIN) {
		...
		netdev->xdp_features = NETDEV_XDP_ACT_BASIC |
				       NETDEV_XDP_ACT_REDIRECT |
				       NETDEV_XDP_ACT_XSK_ZEROCOPY |
				       NETDEV_XDP_ACT_RX_SG;
		netdev->xdp_zc_max_segs = I40E_MAX_BUFFER_TXD;
	} else {
		/* Relate the VSI_VMDQ name to the VSI_MAIN name ... */

but i40e_config_netdev() also runs for VMDQ2 netdevs, via i40e_vsi_setup():

	switch (vsi->type) {
	/* setup the netdev if needed */
	case I40E_VSI_MAIN:
	case I40E_VSI_VMDQ2:
		ret = i40e_config_netdev(vsi);

Those macvlan-offload "<pf>v%d" netdevs get xdp_features == 0, and
i40e_xdp() rejects every ndo_bpf command on them:

	if (vsi->type != I40E_VSI_MAIN)
		return -EINVAL;

So no native XDP program can be attached there, and xmo_rx_hash can never
be reached on such a netdev.

Does this make the netlink capability report inconsistent?  netdev_nl_dev_fill()
derives the xdp-rx-metadata-features bits purely from the presence of the
callback, with no cross-check against dev->xdp_features:

net/core/netdev-genl.c:netdev_nl_dev_fill() {
	...
#define XDP_METADATA_KFUNC(_, flag, __, xmo)			\
	if (netdev->xdp_metadata_ops && netdev->xdp_metadata_ops->xmo)	\
		xdp_rx_meta |= flag;
	...
}

which means a VMDQ2 netdev advertises NETDEV_XDP_RX_METADATA_HASH ("Device is
capable of exposing receive packet hash via bpf_xdp_metadata_rx_hash()") while
rejecting XDP entirely.

The follow-up patch adding bpf_xdp_metadata_rx_vlan_tag() extends the same
unconditional assignment, so NETDEV_XDP_RX_METADATA_VLAN_TAG ends up reported
on those netdevs too; the assignment is still unconditional at the end of the
series.

>  	netdev->watchdog_timeo = 5 * HZ;
>  	i40e_set_ethtool_ops(netdev);
>

-- 
Sashiko AI review · https://netdev-ai.bots.linux.dev/sashiko/#/patchset/20260901211752.1922993-1-anthony.l.nguyen%40intel.com

[PATCH net-next 3/4] i40e: add support for bpf_xdp_metadata_rx_vlan_tag()

[Tony Nguyen]

From: Kohei Enju <kohei@enjuk.jp>

Introduce i40e_xdp_rx_vlan_tag() which takes the same approach as
i40e_process_skb_fields() to extract the VLAN tag from the RX
descriptor.

Tested with X710 adapter using xdp_hw_metadata, and confirmed that VLAN
tags match between bpf_xdp_metadata_rx_vlan_tag() and
skb->vlan_proto/vlan_tci.

Signed-off-by: Kohei Enju <kohei@enjuk.jp>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Tested-by: Patryk Holda <patryk.holda@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index e487d697a634..719f45b5cb40 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -13607,8 +13607,27 @@ static int i40e_xdp_rx_hash(const struct xdp_md *_ctx, u32 *hash,
 	return 0;
 }
 
+static int i40e_xdp_rx_vlan_tag(const struct xdp_md *_ctx, __be16 *vlan_proto,
+				u16 *vlan_tci)
+{
+	const struct i40e_xdp_buff *ctx = (const void *)_ctx;
+	const union i40e_rx_desc *desc = ctx->desc;
+	u64 status;
+
+	status = le64_to_cpu(desc->wb.qword1.status_error_len);
+
+	if (!(status & BIT(I40E_RX_DESC_STATUS_L2TAG1P_SHIFT)))
+		return -ENODATA;
+
+	*vlan_proto = cpu_to_be16(ETH_P_8021Q);
+	*vlan_tci = le16_to_cpu(desc->wb.qword0.lo_dword.l2tag1);
+
+	return 0;
+}
+
 static const struct xdp_metadata_ops i40e_xdp_metadata_ops = {
 	.xmo_rx_hash		= i40e_xdp_rx_hash,
+	.xmo_rx_vlan_tag	= i40e_xdp_rx_vlan_tag,
 };
 
 static const struct net_device_ops i40e_netdev_ops = {
-- 
2.47.1

[PATCH net-next 4/4] i40e: Avoid repeating RX filter warning

[Tony Nguyen]

From: Chris Packham <chris.packham@alliedtelesis.co.nz>

When the i40e runs out of space for RX filters the driver switches to
promiscuous mode and warns that it has done so. In scenarios with a
large number of these filters this can generate a lot of warnings. For
example:

  $ dmesg -c > /dev/null
  $ ip link add dev br0 type bridge vlan_filtering 1 vlan_default_pvid 1
  $ ip link set dev eth7 master br0
  $ bridge vlan add vid 1 dev eth7 pvid untagged self
  $ bridge vlan add vid 2-4094 dev eth7 tagged
  $ dmesg
  [   25.601705] i40e 0000:01:00.1: Error LIBIE_AQ_RC_ENOSPC, forcing overflow promiscuous on PF
  [   25.601833] i40e 0000:01:00.1: Error LIBIE_AQ_RC_ENOSPC, forcing overflow promiscuous on PF
  [   25.601961] i40e 0000:01:00.1: Error LIBIE_AQ_RC_ENOSPC, forcing overflow promiscuous on PF
  [   25.602088] i40e 0000:01:00.1: Error LIBIE_AQ_RC_ENOSPC, forcing overflow promiscuous on PF
  [   25.602216] i40e 0000:01:00.1: Error LIBIE_AQ_RC_ENOSPC, forcing overflow promiscuous on PF
  [   25.602344] i40e 0000:01:00.1: Error LIBIE_AQ_RC_ENOSPC, forcing overflow promiscuous on PF
  ...

Use test_and_set_bit() so that the warning is only issued when the
driver enables promiscuous mode and not on the addition of subsequent RX
filters.

Signed-off-by: Chris Packham <chris.packham@alliedtelesis.co.nz>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Rinitha S <sx.rinitha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c | 19 +++++++++++--------
 1 file changed, 11 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 719f45b5cb40..abbc71e815ae 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -2412,10 +2412,12 @@ void i40e_aqc_add_filters(struct i40e_vsi *vsi, const char *vsi_name,
 
 	if (fcnt != num_add) {
 		if (vsi->type == I40E_VSI_MAIN) {
-			set_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state);
-			dev_warn(&vsi->back->pdev->dev,
-				 "Error %s adding RX filters on %s, promiscuous mode forced on\n",
-				 libie_aq_str(aq_status), vsi_name);
+			if (!test_and_set_bit(__I40E_VSI_OVERFLOW_PROMISC,
+					      vsi->state)) {
+				dev_warn(&vsi->back->pdev->dev,
+					 "Error %s adding RX filters on %s, promiscuous mode forced on\n",
+					 libie_aq_str(aq_status), vsi_name);
+			}
 		} else if (vsi->type == I40E_VSI_SRIOV ||
 			   vsi->type == I40E_VSI_VMDQ1 ||
 			   vsi->type == I40E_VSI_VMDQ2) {
@@ -2465,10 +2467,11 @@ i40e_aqc_broadcast_filter(struct i40e_vsi *vsi, const char *vsi_name,
 	}
 
 	if (aq_ret) {
-		set_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state);
-		dev_warn(&vsi->back->pdev->dev,
-			 "Error %s, forcing overflow promiscuous on %s\n",
-			 libie_aq_str(hw->aq.asq_last_status), vsi_name);
+		if (!test_and_set_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state)) {
+			dev_warn(&vsi->back->pdev->dev,
+				 "Error %s, forcing overflow promiscuous on %s\n",
+				 libie_aq_str(hw->aq.asq_last_status), vsi_name);
+		}
 	}
 
 	return aq_ret;
-- 
2.47.1

Re: [PATCH net-next 4/4] i40e: Avoid repeating RX filter warning

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:

New issues:
- [High] The fix for repeating RX filter warnings is incomplete and leaves SRIOV/VMDQ VSIs vulnerable to log spam, exacerbated by unconditional state clearing for untrusted VFs.

Pre-existing issues:
- [High] The function `i40e_sync_vsi_filters` implements an ad-hoc sleeping spinlock using a bit flag (`__I40E_VSI_SYNCING_FILTERS`), violating subsystem locking guidelines.
--

commit e12ee63ee282f8dda3570d0ba1ab6d4fc31ab63e
Author: Chris Packham <chris.packham@alliedtelesis.co.nz>
Subject: i40e: Avoid repeating RX filter warning

This patch introduces a test_and_set_bit check on the overflow promiscuous
state flag to suppress repetitive log messages when the driver forces
overflow promiscuous mode due to a lack of space for RX filters. It updates
the warning logic in both i40e_aqc_add_filters and i40e_aqc_broadcast_filter.

> diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
> index 719f45b5cb409..abbc71e815ae3 100644
> --- a/drivers/net/ethernet/intel/i40e/i40e_main.c
> +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
[ ... ]
> @@ -2412,10 +2412,12 @@ void i40e_aqc_add_filters(struct i40e_vsi *vsi, const char *vsi_name,
>  
>  	if (fcnt != num_add) {
>  		if (vsi->type == I40E_VSI_MAIN) {
> -			set_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state);
> -			dev_warn(&vsi->back->pdev->dev,
> -				 "Error %s adding RX filters on %s, promiscuous mode forced on\n",
> -				 libie_aq_str(aq_status), vsi_name);
> +			if (!test_and_set_bit(__I40E_VSI_OVERFLOW_PROMISC,
> +					      vsi->state)) {
> +				dev_warn(&vsi->back->pdev->dev,
> +					 "Error %s adding RX filters on %s, promiscuous mode forced on\n",
> +					 libie_aq_str(aq_status), vsi_name);
> +			}
>  		} else if (vsi->type == I40E_VSI_SRIOV ||
>  			   vsi->type == I40E_VSI_VMDQ1 ||
>  			   vsi->type == I40E_VSI_VMDQ2) {

[Severity: High]
Does this logic leave virtual function and vmdq VSIs vulnerable to log spam?
The patch suppresses the warning for the main VSI by checking
test_and_set_bit, but the else if branch for the other VSI types immediately
below it does not use a state check.

Should the state-based warning suppression be enforced equally across all VSI
types?

This regression seems exacerbated by the unconditional state clearing for
untrusted virtual functions in i40e_sync_vsi_filters:

drivers/net/ethernet/intel/i40e/i40e_main.c:i40e_sync_vsi_filters() {
    ...
	/* if the VF is not trusted do not do promisc */
	if (vsi->type == I40E_VSI_SRIOV && pf->vf &&
	    !pf->vf[vsi->vf_id].trusted) {
		clear_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state);
		goto out;
	}
    ...
}

Does this unconditional state clearing destroy the warning suppression logic
for untrusted virtual functions, potentially leading to a denial of service
via log spam?

[Severity: High]
This is a pre-existing issue, but while reviewing the synchronization of
these filters I noticed the following pattern in i40e_sync_vsi_filters:

drivers/net/ethernet/intel/i40e/i40e_main.c:i40e_sync_vsi_filters() {
	...
	while (test_and_set_bit(__I40E_VSI_SYNCING_FILTERS, vsi->state))
		usleep_range(1000, 2000);
	...
out:
	...
	clear_bit(__I40E_VSI_SYNCING_FILTERS, vsi->state);
	return retval;
	...
}

Does this implement an ad-hoc sleeping spinlock using a bit flag, violating
the subsystem guidelines for synchronization?

Would it be better to directly replace this custom polling loop with a
standard mutex to ensure strict lockdep tracking and memory ordering?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260901211752.1922993-1-anthony.l.nguyen@intel.com?part=4

Re: [PATCH net-next 4/4] i40e: Avoid repeating RX filter warning

[netdev-bot+sashiko]

Thank you for your contribution! Sashiko AI review found 1 potential
issue(s) to consider:

Critical: 0 · High: 0 · Medium: 0 (1) · Low: 1

- [Low] Two diagnostics that report different failure classes are now
  gated on one shared single-shot bit.

Pre-existing issues:
- [Medium] The overflow-promiscuous bit that the patch now also uses as a
  log-once latch lives in `vsi->state`, which is protected only by an…

--

i40e: Avoid repeating RX filter warning

The patch converts the two set_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state)
call sites in i40e_aqc_add_filters() and i40e_aqc_broadcast_filter() to
test_and_set_bit(), so the "forcing overflow promiscuous" warning is only
emitted on the transition into overflow promiscuous mode.

> diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
> index 719f45b5cb409..abbc71e815ae3 100644
> --- a/drivers/net/ethernet/intel/i40e/i40e_main.c
> +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
> @@ -2412,10 +2412,12 @@ void i40e_aqc_add_filters(struct i40e_vsi *vsi, const char *vsi_name,
>  
>  	if (fcnt != num_add) {
>  		if (vsi->type == I40E_VSI_MAIN) {
> -			set_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state);
> -			dev_warn(&vsi->back->pdev->dev,
> -				 "Error %s adding RX filters on %s, promiscuous mode forced on\n",
> -				 libie_aq_str(aq_status), vsi_name);
> +			if (!test_and_set_bit(__I40E_VSI_OVERFLOW_PROMISC,
> +					      vsi->state)) {
> +				dev_warn(&vsi->back->pdev->dev,
> +					 "Error %s adding RX filters on %s, promiscuous mode forced on\n",
> +					 libie_aq_str(aq_status), vsi_name);
> +			}

[Severity: Medium]
This isn't a bug introduced by this patch, but the warning is now latched on
a bit whose lifetime is managed by an ad-hoc flag-as-lock scheme, so is the
latch reliable?

i40e_sync_vsi_filters() serializes its whole sleeping section with an
open-coded acquire loop:

	while (test_and_set_bit(__I40E_VSI_SYNCING_FILTERS, vsi->state))
		usleep_range(1000, 2000);
	pf = vsi->back;

	old_overflow = test_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state);

and releases it with a plain clear_bit(__I40E_VSI_SYNCING_FILTERS,
vsi->state) on both the out: and err_no_memory: paths.

i40e_add_vsi(), reached from i40e_rebuild() and i40e_vsi_setup(), clears the
bit without participating in that gate at all:

	spin_unlock_bh(&vsi->mac_filter_hash_lock);
	clear_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state);

If that clear lands while i40e_sync_vsi_filters() is between its
old_overflow snapshot and the new_overflow / promisc_threshold decision, can
the warning re-fire, or the opposite, can the state read as non-overflowing
while filter programming keeps failing?

>  		} else if (vsi->type == I40E_VSI_SRIOV ||
>  			   vsi->type == I40E_VSI_VMDQ1 ||
>  			   vsi->type == I40E_VSI_VMDQ2) {
> @@ -2465,10 +2467,11 @@ i40e_aqc_broadcast_filter(struct i40e_vsi *vsi, const char *vsi_name,
>  	}
>  
>  	if (aq_ret) {
> -		set_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state);
> -		dev_warn(&vsi->back->pdev->dev,
> -			 "Error %s, forcing overflow promiscuous on %s\n",
> -			 libie_aq_str(hw->aq.asq_last_status), vsi_name);
> +		if (!test_and_set_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state)) {
> +			dev_warn(&vsi->back->pdev->dev,
> +				 "Error %s, forcing overflow promiscuous on %s\n",
> +				 libie_aq_str(hw->aq.asq_last_status), vsi_name);
> +		}
>  	}

[Severity: Low]
Two different failure classes now share one single-shot bit. Is that
intended?

i40e_aqc_add_filters() warns when MAC/VLAN filter space is exhausted
(fcnt != num_add, typically LIBIE_AQ_RC_ENOSPC), while
i40e_aqc_broadcast_filter() warns on any AdminQ error returned by
i40e_aq_set_vsi_broadcast() or i40e_aq_set_vsi_bc_promisc_on_vlan(),
including errors that are not ENOSPC, and prints its own
libie_aq_str(hw->aq.asq_last_status) text.

In the scenario from the commit message (bridge vlan add vid 2-4094) the add
path sets __I40E_VSI_OVERFLOW_PROMISC first, so a later
i40e_aqc_broadcast_filter() failure of an unrelated class prints nothing
until the bit is cleared again.

For the delete path in i40e_sync_vsi_filters() the return value is
discarded:

			if (is_broadcast_ether_addr(f->macaddr)) {
				i40e_aqc_broadcast_filter(vsi, vsi_name, f);

				hlist_del(&f->hlist);
				kfree(f);
				continue;
			}

so with the warning suppressed, is that failure reported anywhere at all?
Would a per-site dev_warn_once() style latch, or a separate condition flag
per message, keep both diagnostics?

-- 
Sashiko AI review · https://netdev-ai.bots.linux.dev/sashiko/#/patchset/20260901211752.1922993-1-anthony.l.nguyen%40intel.com